© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18058
    Prev
    Next
    INDEX
    Explanations

    random walk, trees, steps, matrix, group theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vin
    -0.08
    vin
    -0.06
    resa
    -0.06
     sing
    -0.06
     nesting
    -0.06
    anf
    -0.06
    稼
    -0.06
    isme
    -0.06
    ç¨ļå«©
    -0.06
     server
    -0.06
    POSITIVE LOGITS
     directions
    0.09
    æĭīå¾·
    0.09
    Compiled
    0.08
    禦
    0.08
    #undef
    0.08
    åĩºåħ¥
    0.08
    Directions
    0.08
    (direction
    0.08
    compass
    0.08
    á»ĭp
    0.08
    Activations Density 0.011%

    No Known Activations